A Monitoring and Adapting Intelligence Assistant (MAIA)

Intelligence analysts need help managing a barrage of tasks and flood of information while overcoming cognitive limitations. That help must respond to their individual time-varying needs and context. Challenges include (1) sensing analysts"situations; (2) tracking their interests and needs; (3) managing information flows; (4) facilitating user focus and understanding; and (5) controlling and orchestrating the above capabilities. The keys to adaptive analyst support include (a) access to user/situational data; (b) characterization of the relevant features latent in that data; (c) correlating features with known cognitive biases, failure modes, and support needs; and (d) application of appropriate learning and control mechanisms to map from situational features to system actions. We propose to develop technology for a Monitoring and Adapting Intelligence Assistant (MAIA). During Phase I we will identify use cases and requirements; use those to flesh out the general challenges and capabilities sketched above; outline a technology and follow-on research framework to address those needs; and design and prototype subsets of the overall vision to demonstrate feasibility. We expect to focus development work on mapping from user activity to metacognitive prompts and information-sharing actions. Finally, we will develop a Phase II plan to follow through on design, development, and transition.